Show simple item record

dc.contributor.authorKhalilov, Maxim
dc.contributor.authorRodríguez Fonollosa, José Adrián
dc.contributor.authorZamora Martínez, Francisco
dc.contributor.authorCastro Bleda, María José
dc.contributor.authorEspaña Boquera, Salvador
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions
dc.date.accessioned2013-12-31T08:47:39Z
dc.date.available2013-12-31T08:47:39Z
dc.date.created2013-12-20
dc.date.issued2013-12-20
dc.identifier.citationKhalilov, M. [et al.]. Neural network language models to select the best translation. "Computational Linguistics in the Netherlands Journal", 20 Desembre 2013, vol. 3, p. 217-233.
dc.identifier.issn2211-4009
dc.identifier.urihttp://hdl.handle.net/2117/21106
dc.description.abstractThe quality of translations produced by statistical machine translation (SMT) systems crucially depends on the generalization ability provided by the statistical models involved in the process. While most modern SMT systems use n-gram models to predict the next element in a sequence of tokens, our system uses a continuous space language model (LM) based on neural networks (NN). In contrast to works in which the NN LM is only used to estimate the probabilities of shortlist words (Schwenk 2010), we calculate the posterior probabilities of out-of-shortlist words using an additional neuron and unigram probabilities. Experimental results on a small Italian- to-English and a large Arabic-to-English translation task, which take into account di erent word history lengths (n-gram order), show that the NN LMs are scalable to small and large data and can improve an n-gram-based SMT system. For the most part, this approach aims to improve translation quality for tasks that lack translation data, but we also demonstrate its scalability to large-vocabulary tasks.
dc.format.extent17 p.
dc.language.isoeng
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 Spain
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Llenguatge natural
dc.subject.lcshNatural language processing (Computer science)
dc.subject.lcshAutomatic speech recognition
dc.titleNeural network language models to select the best translation
dc.typeArticle
dc.subject.lemacTractament del llenguatge natural (Informàtica)
dc.subject.lemacReconeixement automàtic de la parla
dc.contributor.groupUniversitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttp://clinjournal.org/sites/default/files/13-Khalilov-etal-CLIN2013.pdf
dc.rights.accessOpen Access
local.identifier.drac12952247
dc.description.versionPostprint (published version)
local.citation.authorKhalilov, M.; Fonollosa, José A. R.; Zamora-Martínez, F.; Castro-Bleda, M.J.; España-Boquera, S.
local.citation.publicationNameComputational Linguistics in the Netherlands Journal
local.citation.volume3
local.citation.startingPage217
local.citation.endingPage233


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-NoDerivs 3.0 Spain
Except where otherwise noted, content on this work is licensed under a Creative Commons license : Attribution-NonCommercial-NoDerivs 3.0 Spain